Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9533
    Prev
    Next
    INDEX
    Explanations

    punctuations and markers indicating the presence of notes or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.08
    2:0.04
    3:0.05
    4:0.03
    5:0.05
    6:0.12
    7:0.08
    8:0.04
    9:0.05
    10:0.22
    11:0.13
    Negative Logits
     Reloaded
    -2.27
     tomorrow
    -2.25
     auctions
    -1.96
     auction
    -1.96
     Grill
    -1.94
     Ware
    -1.91
     tonight
    -1.91
     Ore
    -1.87
    ials
    -1.87
     Roof
    -1.85
    POSITIVE LOGITS
    c
    2.87
    archive
    2.35
    coll
    2.35
    cond
    2.31
    kB
    2.29
    morph
    2.28
    cb
    2.23
    bat
    2.23
    visual
    2.21
    vis
    2.21
    Activations Density 0.000%

    No Known Activations